{"as_of":"2026-08-19T03:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5ccd54767833f73406c7a1a657563ae3196bf4d3a82f7f06d9894c86f078c83d","coverage":[{"denominator":55,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T22:07:08.703692Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2603.04438/citation-record","integrity":"/paper/2603.04438/integrity","json":"/paper/2603.04438/citation-record.json","paper":"/paper/2603.04438"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:05.674320Z","title":"Modern diagnostic imaging technique applications and risk factors in the medical field: a review,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:05.674320Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:b901871c94c9f47c7378bca4ad7b7b7a1c8ffa80e295a32d3e98bcacf01c3bde","observation_id":"02f81aab-88f3-4e59-a914-841a5136146c","resolution":{"observed_at":"2026-08-02T22:07:05.674320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:05.731957Z","title":"Next-generation mri scanner designed for ultra- high-resolution human brain imaging at 7 tesla,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:05.731957Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:1f558305807b172f1aa3bf03c58cb186bdc97b95177b703f469363d80df116ff","observation_id":"d799dae7-b482-4c5f-ac70-4686454e96e4","resolution":{"observed_at":"2026-08-02T22:07:05.731957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:05.768135Z","title":"2.5-minute fast brain mri with multiple contrasts in acute ischemic stroke,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:05.768135Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:04d12238eb029a0a754c9aaf771d15f334bab64ae15e75f768a92d68369f314b","observation_id":"236d7b72-4426-4caa-b2ac-b89b2c1feb8e","resolution":{"observed_at":"2026-08-02T22:07:05.768135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:05.783037Z","title":"Emerging techniques in cardiac magnetic resonance imaging,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:05.783037Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:1b26cfd86a7f9561af448ba706c038ee5269cf47d1ec8470f433ede6cc973ed1","observation_id":"9fcf093b-f157-4e04-9b1b-d88f1b25b9fc","resolution":{"observed_at":"2026-08-02T22:07:05.783037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:05.829015Z","title":"Compressed sensing: From research to clinical practice with deep neural networks: Shortening scan times for magnetic resonance imaging,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:05.829015Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:afc4f93d0d07a1adca7da7b238cd1c83b32add0b99d2edca79066f1759b9a7d1","observation_id":"3ec60201-b4f0-4d0d-a289-11c4c4939cba","resolution":{"observed_at":"2026-08-02T22:07:05.829015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:05.865046Z","title":"Recent advances in parallel imaging for mri: Wave-caipi technique,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:05.865046Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:f62b3bd33c62f13181b67d91bb06ec9084380420d7f83fe08decb04050255906","observation_id":"f81d5101-1156-40e5-9b81-2058ac16172a","resolution":{"observed_at":"2026-08-02T22:07:05.865046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:05.894065Z","title":"A review on accel- erated magnetic resonance imaging techniques: Parallel imaging, compressed sensing, and machine learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:05.894065Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:4e1f4f843ef059614a4139421ce0acee756bb045d8e94197f4cc4b6f55fab0cf","observation_id":"84c52881-1318-48eb-bdd6-6b8bc8759363","resolution":{"observed_at":"2026-08-02T22:07:05.894065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:05.934049Z","title":"An introduction to deep generative modeling,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:05.934049Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:dcbb5bb54f217b9d94bcc95e70e0a4ffe6fe6986c550197cbcc7bdc8671f03f7","observation_id":"486ec862-1469-426f-a859-ef42ea34a98b","resolution":{"observed_at":"2026-08-02T22:07:05.934049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:05.947651Z","title":"A survey of multimodal deep generative models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:05.947651Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:cd3e19da89f8cbcd8daad513b297ac2a019a19a26961e82d5ffcbd3e9fb385a9","observation_id":"2339a3be-937d-40d4-97e6-f8a6ad616506","resolution":{"observed_at":"2026-08-02T22:07:05.947651Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.004734Z","title":"Mathematical models for magnetic resonance imaging reconstruction: An overview of the approaches, problems, and future research areas,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.004734Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:8afc1f03596f01b907c325920f58a2debf6333caade6f29cef8f811371ce996d","observation_id":"2241abb4-52a4-4224-99a7-6217c16659f1","resolution":{"observed_at":"2026-08-02T22:07:06.004734Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.033940Z","title":"Dagan: Deep de-aliasing generative adversarial networks for fast compressed sensing mri reconstruction,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.033940Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:3bc0a8764128609d808ed065de68f1155dadeb5297aa0981274e2d13673e0953","observation_id":"273dfa1e-5edd-4238-9d57-9dc88664ca07","resolution":{"observed_at":"2026-08-02T22:07:06.033940Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.092926Z","title":"Com- pressed sensing mri reconstruction using a generative adversarial network with a cyclic loss,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.092926Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:5d28cd1c4c81679e933aa82b0298f87ed61f5835af84ac537b6f61e743056774","observation_id":"7841db65-a0f7-4bfe-aa77-ad5fd324873c","resolution":{"observed_at":"2026-08-02T22:07:06.092926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.118736Z","title":"High quality and fast compressed sensing mri reconstruction via edge-enhanced dual discriminator generative adversarial network,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.118736Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:3063fa7560c17e02a82f57f0a1550717df91e89ae82cc0a24a9b64381503fccf","observation_id":"ab0326bc-d668-4ba6-854c-e9d4b467255d","resolution":{"observed_at":"2026-08-02T22:07:06.118736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.179167Z","title":"Unpaired deep learning for accelerated mri using optimal transport driven cyclegan,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.179167Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:a11da5f1adf244d130bb8d7290e1d6e225f9e0d859a91d53242e21a55630441e","observation_id":"e08779dd-4816-4915-b15f-899e9de74129","resolution":{"observed_at":"2026-08-02T22:07:06.179167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.237680Z","title":"Learning mri artefact removal with unpaired data,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.237680Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:f8b9ee6b399f4530a0ed3e0faf1007e0dbe3b584e6c607c9522101f017e8b25d","observation_id":"504f0058-7589-47e9-a01b-f797fe4345d3","resolution":{"observed_at":"2026-08-02T22:07:06.237680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.266720Z","title":"Time-dependent deep image prior for dynamic mri,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.266720Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:78639351a6cb87137c5571794bf1c748272fd8803dfe0c090cde98bb79539171","observation_id":"a1bc0976-e5d5-4eea-889b-b790055b517f","resolution":{"observed_at":"2026-08-02T22:07:06.266720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.321165Z","title":"Accelerated mri with un-trained neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.321165Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:03bb9861b15437f2734937de6701b080f2bcc31feccf0f825eb370c39a0b835a","observation_id":"92476901-db77-4d0d-84af-cd788ccc8770","resolution":{"observed_at":"2026-08-02T22:07:06.321165Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.349576Z","title":"Nerp: implicit neural representation learning with prior embedding for sparsely sampled image reconstruction,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.349576Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:9ee82f723a832b93aa25e505a04cba318afba0bc483dcbaea5a461a3b8bbc40a","observation_id":"a21923a9-688c-418f-a025-727f28d2cce2","resolution":{"observed_at":"2026-08-02T22:07:06.349576Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.404191Z","title":"Pearl: Cascaded self-supervised cross-fusion learning for parallel mri acceleration,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.404191Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:1bc3415e6d7b4523b2e3d1b90a8bdb0b5bc7f463d895b38ed7dbd86d18575062","observation_id":"908f83df-3f6a-466c-8b92-1deb3cae3607","resolution":{"observed_at":"2026-08-02T22:07:06.404191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.435202Z","title":"Analysis of deep image prior and exploiting self-guidance for image reconstruction,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.435202Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:33f1b341d04875a3dc226564e274a38eae70e3cddc6b9a097182ed4055bc53bb","observation_id":"37a6d5ef-c166-48d2-bdd1-a9c7bcc048d9","resolution":{"observed_at":"2026-08-02T22:07:06.435202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.516291Z","title":"The development of cognitive load theory: Replication crises and incorporation of other theories can lead to theory expansion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.516291Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:ed1ca9523921b4ba5a7770096dbd6fb0a58a17d9d94fc38bc19c6a154bc4c10e","observation_id":"de498dfb-ec53-4179-8a92-fdfea5e3efb0","resolution":{"observed_at":"2026-08-02T22:07:06.516291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.572135Z","title":"A cognitive load theory approach to defining and measuring task complexity through element interactivity,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.572135Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:476d404fd19fc15facc616a0f6a5c3ebb97312c642f3a611ab78b0e03b6aa140","observation_id":"d418bc23-a3c2-4b6e-a8db-d0eb36760872","resolution":{"observed_at":"2026-08-02T22:07:06.572135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.604099Z","title":"Self-paced curriculum learning,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.604099Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:262181de86252b81a3242192830876c4e50be90b290763898ae1f7eee4b56129","observation_id":"7eb1ffa7-8707-4247-837b-0b17e6a25495","resolution":{"observed_at":"2026-08-02T22:07:06.604099Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.660208Z","title":"Leveraging prior-knowledge for weakly supervised object detection under a collaborative self-paced curriculum learning framework,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.660208Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:9ecf5ba6c52523c5eebfdf4001fa3a898d50254a0c5b360de157ee52a18a713e","observation_id":"b9b12ff9-c49a-4e77-a644-27005fcb09ef","resolution":{"observed_at":"2026-08-02T22:07:06.660208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.00904","last_updated":"2018-06-06T06:46:02Z","snapshot_observed_at":"2026-08-14T19:58:23.751246Z","submitted_at":"2018-01-03T05:49:37Z","title":"ScreenerNet: Learning Self-Paced Curriculum for Deep Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.00904","snapshot_observed_at":"2026-08-02T22:07:06.693896Z","title":"Screenernet: Learning self-paced curriculum for deep neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.693896Z"},"links":{"cited_paper":"/paper/1801.00904","citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:e241a305dd9307548280448bb4100fab88af93d37a4e8ef26bdd3508ab559a61","observation_id":"6428cba5-0440-455f-a9bb-a4c8e1b760d4","resolution":{"observed_at":"2026-08-02T22:07:06.693896Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.747252Z","title":"Brain-guided self- paced curriculum learning for adaptive human–machine interfaces,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.747252Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:274340c70caba06059a208f029800386c116c07ad6bc692ca5b6c7d6e1687ff8","observation_id":"f4ee2143-3a62-4a32-b921-3584a66682c3","resolution":{"observed_at":"2026-08-02T22:07:06.747252Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.836014Z","title":"Phase retrieval using untrained neural network priors,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.836014Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:03203de2432306d097139edc49074035c88fe16172ffb6f14d4c1963cbccb868","observation_id":"04b327a3-eb45-4158-a687-fd0c2e950c66","resolution":{"observed_at":"2026-08-02T22:07:06.836014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.901421Z","title":"Deeptensor: Low-rank tensor decomposition with deep network priors,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.901421Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:f5f250ef503cafd008703184a334e3dbe34388c6d61add4c23807eea13f24097","observation_id":"e22efd32-c7b9-426e-b0df-8e4da4be9e60","resolution":{"observed_at":"2026-08-02T22:07:06.901421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:06.994798Z","title":"Denoising and regular- ization via exploiting the structural bias of convolutional generators,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:06.994798Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:07c42e43aeac53cb742340beba6e1f7ff01bf3c70acf1f9014b489b65909be49","observation_id":"322535ad-7067-44b5-8928-db4b7a7ded6e","resolution":{"observed_at":"2026-08-02T22:07:06.994798Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.043665Z","title":"Convergence guarantees of overparametrized wide deep inverse prior,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.043665Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:8cc3cac17ed8eb4486bfc17ecdef8525204338d77668599c5c95aafe28d9200e","observation_id":"b4690849-6e42-4013-a4d2-00fd7a1415e4","resolution":{"observed_at":"2026-08-02T22:07:07.043665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.139598Z","title":"Convergence and recovery guarantees of unsupervised neural networks for inverse problems,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.139598Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:5e30214a9a53e4fef0935f5c1a9981940c53269208d7718a8a1b73407db88358","observation_id":"94faf30c-c207-41e7-a14c-4fa3b37ba830","resolution":{"observed_at":"2026-08-02T22:07:07.139598Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.185931Z","title":"Curriculum learning,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.185931Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:51993657023f9672b864fb7b55c1b2ca3895d3959750da8293d5cb1a84228b6b","observation_id":"ba677fe6-5479-4368-9f38-8bf43d56b7a2","resolution":{"observed_at":"2026-08-02T22:07:07.185931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.261073Z","title":"Self-paced learning for latent variable models,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.261073Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:e05c947d90b1a5344e80c8bdfb909825b4d3252c76f3ee6d505df6fa52bcc24e","observation_id":"0d3bc8fc-a8e9-47e4-8fe3-b9f78bd5dc54","resolution":{"observed_at":"2026-08-02T22:07:07.261073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.331334Z","title":"A theoretical understand- ing of self-paced learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.331334Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:d53fda5aa6c460f045fa026efb41b729807aa0a428a7d50f4d13eaa750c5347a","observation_id":"9bb8916e-1822-44af-b694-587d052f07bf","resolution":{"observed_at":"2026-08-02T22:07:07.331334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.395913Z","title":"Self-paced learning with diversity,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.395913Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:df274fb35fd64f893fbc13c241a81ca5e8b3ccdd1ac17394404b7eacbf6b6a33","observation_id":"8d54e877-f2c6-4b10-aa49-91c6c00454b5","resolution":{"observed_at":"2026-08-02T22:07:07.395913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.451656Z","title":"Modl: Model- based deep learning architecture for inverse problems,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.451656Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:aa13f98cb21bf7d75dc715c02bcee15a2a563786fd1af774cb21e9f6a4b8c178","observation_id":"c6a0d5e3-e92f-4768-b155-f3c49768dbdd","resolution":{"observed_at":"2026-08-02T22:07:07.451656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.519803Z","title":"fastmri: A publicly available raw k- space and dicom dataset of knee images for accelerated mr image reconstruction using machine learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.519803Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:39621de33daa2eef45322004b8410334fb9d846e91a757a24439903e075e805e","observation_id":"ff8543fa-5f53-4922-a395-187028cda60b","resolution":{"observed_at":"2026-08-02T22:07:07.519803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.575569Z","title":"Incorporating reference in parallel imaging and compressed sensing,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.575569Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:c391c19cb3324efc2bcf6037ab9129cbc063a8c07ea5dad1b7a8e43f0a8916d0","observation_id":"6a63f8e1-2ac4-4683-8dd9-b2eabccef6b4","resolution":{"observed_at":"2026-08-02T22:07:07.575569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.642320Z","title":"Image restora- tion using total variation regularized deep image prior,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.642320Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:d3e6fe10d26a91177039c92e24958e59aae6ecfcf80ddab65a2e58e94e2342ee","observation_id":"e2737ec8-1e50-460a-8e9a-b36bdff826fe","resolution":{"observed_at":"2026-08-02T22:07:07.642320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.694980Z","title":"Decoupled algorithm for mri reconstruc- tion using nonlocal block matching model: Bm3d-mri,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.694980Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:ad45a20ab88faf012136fadfad432ee2cfddd159b05739bda92188c93b9c6c7d","observation_id":"3f1d82db-f0d0-4603-ad57-36863195ac34","resolution":{"observed_at":"2026-08-02T22:07:07.694980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.762762Z","title":"An unsupervised method for mri recovery: deep image prior with structured sparsity,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.762762Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:97494626a94e4ee13e566ced5fe59910385f28df6a424a4c6dd7e6e79d791c21","observation_id":"082974ac-fc94-4073-9dde-f7738bf0bdee","resolution":{"observed_at":"2026-08-02T22:07:07.762762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.826797Z","title":"Self-supervised learning of physics-guided reconstruction neural networks without fully sampled reference data,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.826797Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:9ad2f067b1699b68b2af6150c7503f35fcd9ac8c16a0776347f87a444ecb8146","observation_id":"3d309e1f-8900-4eb7-bd36-61c9294a2b37","resolution":{"observed_at":"2026-08-02T22:07:07.826797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.888639Z","title":"Image reconstruction via autoencoding sequential deep image prior,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.888639Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:cbad9ca42915ee9cc82a1921aa4d8c3d66c9f6d1f4e880eae921380acd4b4db8","observation_id":"e7ee2953-758c-4edc-ac61-050f936dea0a","resolution":{"observed_at":"2026-08-02T22:07:07.888639Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:07.951824Z","title":"Spatiotemporal implicit neural representation for unsupervised dynamic mri re- construction,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:07.951824Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:be72418d432cc36dfca0cc1d23e40d067497a25b6e6df08c1352a038ef130e3a","observation_id":"603ed465-ebde-4458-9387-c3946f9406f0","resolution":{"observed_at":"2026-08-02T22:07:07.951824Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:08.014441Z","title":"Learning interpretable decision rule sets: A submodular optimization approach,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.014441Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:fabc8c11b289606271e94b6842a6d3e6e1b285dbf73071008b3d40089fbf8826","observation_id":"5c705907-69c0-4202-9647-9f4ca343f9aa","resolution":{"observed_at":"2026-08-02T22:07:08.014441Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:08.123117Z","title":"Data- efficient structured pruning via submodular optimization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.123117Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:e62711887e96c97fbd36b6d81840942f8a0b88a223d8b281ae990a54d2e5ba26","observation_id":"06b70ba8-c64a-475c-b8fe-17636473cf13","resolution":{"observed_at":"2026-08-02T22:07:08.123117Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:08.201013Z","title":"Greedy guarantees for minimum submodular cost submodular/non-submodular cover problem,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.201013Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:999475fe746c9d36ad531d3d1cec35bda7a2f5899a11ec53e8ae4e929b82a887","observation_id":"d5324af4-5ca3-446a-9fe3-f516bca55802","resolution":{"observed_at":"2026-08-02T22:07:08.201013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:08.296808Z","title":"Weak submodularity implies localizability: Local search for constrained non- submodular function maximization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.296808Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:d1c4805b59bf876962fc1c8ea5a54f1ead898dac44d6b681c70390f8a468454f","observation_id":"4b9651bf-f44d-4504-8f50-c7b337260fb5","resolution":{"observed_at":"2026-08-02T22:07:08.296808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:08.368298Z","title":"Neural tangent kernel: Convergence and generalization in neural net- works,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.368298Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:e887020ffc896c947aa295e1eb9bd8048de4a15557aa475a109d58e4088a52de","observation_id":"5b9e6b40-846c-44ee-95cc-676928a36a44","resolution":{"observed_at":"2026-08-02T22:07:08.368298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.13614","last_updated":"2022-08-29T14:05:54Z","snapshot_observed_at":"2026-08-17T18:06:39.308458Z","submitted_at":"2022-08-29T14:05:54Z","title":"Neural Tangent Kernel: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.13614","snapshot_observed_at":"2026-08-02T22:07:08.425628Z","title":"Neural tangent kernel: A survey,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.425628Z"},"links":{"cited_paper":"/paper/2208.13614","citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:d67972750c40013dd12129bad85875dd06602ad29ea094eac0012338c88288c1","observation_id":"8dc777f8-fc54-422c-8d90-04147d5b6ab8","resolution":{"observed_at":"2026-08-02T22:07:08.425628Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:08.485556Z","title":"Neural net- works can learn representations with gradient descent,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.485556Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:6e7ffbbb0a0a3c2ccf57e31688a4aaf53e1d181459c1889f74e91165b00361ac","observation_id":"a433755c-f605-47e1-9d38-509b31e8f4e1","resolution":{"observed_at":"2026-08-02T22:07:08.485556Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:08.543455Z","title":"Linear convergence of gradient and proximal-gradient methods under the polyak- lojasiewicz condition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.543455Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:40b398e3556e1ff596f9e44c1b7a6402795bba0eac4a2a99a27ed82b6cc056a8","observation_id":"c6f47c6d-cd7e-4e69-9b3c-7f4f5d8bca3e","resolution":{"observed_at":"2026-08-02T22:07:08.543455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02422","last_updated":"2023-10-05T21:57:43Z","snapshot_observed_at":"2026-08-16T15:26:45.916895Z","submitted_at":"2023-06-04T17:54:11Z","title":"A Generalized Alternating Method for Bilevel Learning under the Polyak-{\\L}ojasiewicz Condition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02422","snapshot_observed_at":"2026-08-02T22:07:08.605216Z","title":"A generalized alternat- ing method for bilevel learning under the polyak-{\\L} ojasiewicz condition,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.605216Z"},"links":{"cited_paper":"/paper/2306.02422","citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:cc8e1026711c43c265acb2635c24afe104d6ccfe610e5af0a3f2a067bd0483d7","observation_id":"e770844c-0903-4a5b-8789-a2766d1af217","resolution":{"observed_at":"2026-08-02T22:07:08.605216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:08.669881Z","title":"Polyak-{\\L}ojasiewicz inequality is es- sentially no more general than strong convexity for𝑐 2 functions,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.669881Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:4b3232998317ed23a5f769cd6802875de60a61238d91331ee64b5b9da2141da5","observation_id":"f6a1f28e-f338-4159-9048-4fa7c94f955a","resolution":{"observed_at":"2026-08-02T22:07:08.669881Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T22:07:08.703692Z","title":"Range restricted iterative methods for linear discrete ill-posed problems,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-02T22:07:08.703692Z"},"links":{"citing_paper":"/paper/2603.04438"},"observation_digest":"sha256:1de13bc1b79c9240df3b34e1edca2e18db01df352de004838c96119ab167114f","observation_id":"87a53eaf-71ed-43aa-8c71-838683754500","resolution":{"observed_at":"2026-08-02T22:07:08.703692Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.04438","last_updated":"2026-06-16T07:46:11Z","latest_version":3,"primary_category":"eess.IV","snapshot_observed_at":"2026-08-17T02:40:57.525434Z","submitted_at":"2026-02-20T07:20:52Z","title":"CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction"},"reference_resolution":{"displayed":55,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":55,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":55},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2603.04438."}